Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.4779. Min Act: -0.1700

Data Index: 1466268 (Open Web Text)

Max Activating Token Index: 850

Text #1

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.2328. Min Act: -0.1700

Data Index: 8325492 (Open Web Text)

Max Activating Token Index: 680

Text #2

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.1883. Min Act: -0.1700

Data Index: 6473404 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.2078. Min Act: -0.1700

Data Index: 5355866 (Open Web Text)

Max Activating Token Index: 765

Text #4

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.1267. Min Act: -0.1700

Data Index: 3644695 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.1037. Min Act: -0.1700

Data Index: 1761203 (Open Web Text)

Max Activating Token Index: 766

Text #6

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0586. Min Act: -0.1700

Data Index: 3002649 (Open Web Text)

Max Activating Token Index: 885

Text #7

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0481. Min Act: -0.1700

Data Index: 5924480 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0869. Min Act: -0.1700

Data Index: 6580388 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0477. Min Act: -0.1700

Data Index: 1033775 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0277. Min Act: -0.1700

Data Index: 1106002 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0490. Min Act: -0.1700

Data Index: 8422052 (Open Web Text)

Max Activating Token Index: 876

Text #12

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0240. Min Act: -0.1700

Data Index: 8126423 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 4.4779. Min Range: -4.4779

Max Act: 3.9881. Min Act: -0.1700

Data Index: 4872951 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 4.4779. Min Range: -4.4779

Max Act: 4.0005. Min Act: -0.1700

Data Index: 424076 (Open Web Text)

Max Activating Token Index: 990

Text #15

Max Range: 4.4779. Min Range: -4.4779

Max Act: 3.9971. Min Act: -0.1700

Data Index: 3020995 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 4.4779. Min Range: -4.4779

Max Act: 3.9975. Min Act: -0.1700

Data Index: 8543604 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 4.4779. Min Range: -4.4779

Max Act: 3.9404. Min Act: -0.1700

Data Index: 8150788 (Open Web Text)

Max Activating Token Index: 728

Text #18

Max Range: 4.4779. Min Range: -4.4779

Max Act: 3.9808. Min Act: -0.1700

Data Index: 7686441 (Open Web Text)

Max Activating Token Index: 792

Text #19

Max Range: 4.4779. Min Range: -4.4779

Max Act: 3.9557. Min Act: -0.1700

Data Index: 3234489 (Open Web Text)

Max Activating Token Index: 427